Variational Denoising Network: Toward Blind Noise Modeling and Removal

Abstract

Blind image denoising is an important yet very challenging problem in computer vision due to the complicated acquisition process of real images. In this work we propose a new variational inference method, which integrates both noise estimation and image denoising into a unique Bayesian framework, for blind image denoising. Specifically, an approximate posterior, parameterized by deep neural networks, is presented by taking the intrinsic clean image and noise variances as latent variables conditioned on the input noisy image. This posterior provides explicit parametric forms for all its involved hyper-parameters, and thus can be easily implemented for blind image denoising with automatic noise estimation for the test noisy image. On one hand, as other data-driven deep learning methods, our method, namely variational denoising network (VDN), can perform denoising efficiently due to its explicit form of posterior expression. On the other hand, VDN inherits the advantages of traditional model-driven approaches, especially the good generalization capability of generative models. VDN has good interpretability and can be flexibly utilized to estimate and remove complicated non-i.i.d. noise collected in real scenarios. Comprehensive experiments are performed to substantiate the superiority of our method in blind image denoising.

arXiv commentCorrect a minor typo

Cited by in corpus (35)

• Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
• Uformer: A General U-Shaped Transformer for Image Restoration
• Variational Deep Image Restoration
• Learning Enriched Features for Real Image Restoration and Enhancement
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• Multi-Stage Progressive Image Restoration
• Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
• HINet: Half Instance Normalization Network for Image Restoration
• Deep Learning on Image Denoising: An overview
• Selective Residual M-Net for Real Image Denoising
• NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• Invertible Denoising Network: A Light Solution for Real Noise Removal
• RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining
• Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
• Joint self-supervised blind denoising and noise estimation
• FINO: Flow-based Joint Image and Noise Model
• Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
• Unpaired Learning of Deep Image Denoising
• Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
• Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
• Noise2Blur: Online Noise Extraction and Denoising
• Learning Model-Blind Temporal Denoisers without Ground Truths
• Adaptive noise imitation for image denoising
• Dynamic Slimmable Denoising Network
• Searching Efficient Model-guided Deep Network for Image Denoising
• Enhancing and Learning Denoiser without Clean Reference
• ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoising
• Self-Verification in Image Denoising
• Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
• Variational Deep Image Denoising